Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11707
    Prev
    Next
    INDEX
    Explanations

    phrases related to abusive or harmful situations and mental health struggles

    oai_token-act-pair · gpt-3.5-turbo

    themes related to abuse and mental health struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slic
    -0.79
     meteor
    -0.75
    £ı
    -0.74
    ouver
    -0.74
     Manufact
    -0.72
    VEL
    -0.71
     printers
    -0.69
     manned
    -0.68
     revolutions
    -0.68
     imports
    -0.68
    POSITIVE LOGITS
     counselling
    1.15
     counselors
    1.15
     trauma
    1.07
     counselor
    1.04
     counseling
    1.04
     traumatic
    1.02
    ilitating
    1.02
    endered
    0.99
     therapy
    0.98
    abuse
    0.97
    Activations Density 0.288%

    No Known Activations